 |
These WINKS statistics tutorials explain the use and interpretation of standard statistical analysis techniques for Medical, Pharmaceutical, Clinical Trials, Marketing or Scientific Research. The examples include how-to instructions for WINKS SDA Version 6.0 Software. Download evaluation copy of WINKS. |
Preparing Excel Data for
Import into WINKS
Guidelines for preparing data in Excel for import
into the WINKS statistics program:
1. Names of columns, which will become variable
names, should be short and unique, 8 characters or less, containing no
blanks. Names must begin with a letter. For example AGE1998 is okay but
1998AGE is not. Also “AGE 1999�is not an allowed variable name, but
AGE_1999 is okay. Names should appear on row 1 in the spreadsheet above
each variable column.
2. Data in columns should be coded. WINKS allows up
to 65 characters in a character field. However, long entries become
difficult to analyze. For example, code data as “INFLUENZA�or “FLU�
rather than “PATIENT HAS INFLUENZA.�We recommend that data field codes be
8 characters long or shorter. Also, make sure that all character (text)
data fields are in either all upper or all lower case. The computer sees
the character “F�different from “f�and “FEMALE�different from “Female.�/p>
3. If you want to calculate averages, all data in a
column must be numeric. You should have no numeric data entered as a range
such as 30-50, or that contains any other character other than a number.
For example the entries “GT 50,��lt;=100�or �00+�“N.A.�or “MISSING�
cannot be used to create a mean. Also, large numbers should be entered
without commas Use �23456�instead of �23,456.�Anything in a data field
other than numeric digits, decimal points and a preceding plus (+) or
minus (-) cannot be used to calculate averages.
4. If you have missing values in a column of number,
select a unique identifier such as -9 or -99 (some impossible number) and
enter it into the fields that are missing. After you import the data into
WINKS, specify -9 or -99 as the missing value code and WINKS will ignore
any missing entries during analysis. See the WINKS manual for specifying
missing data codes.
Here is an example file ready for import:
5. Once you've created and saved the Excel file you
can open it difrectly into WINKS (version 6 and above) by choose
File/Open Data Set -- then specify .xls as the "files of data
type." WINKS will as you if your first row are variable names.
6. For an example of what an Excel file should look
like before importing it, open the Excel file named EXAMPLE.XLS in the
WINKS directory.
For a more comprehensive look at preparing data:
Elliott AC, Hynan LS, Reisch JS, Smith JP. "Preparing Data for Analysis
Using Microsoft Excel." J Investig Med 54(6):334-41, 2006.